Developer Gustavo Enriquez built MakerAI ChatTools, a capability framework that extends AI models with deterministic tools for seeing, hearing, reading, speaking, and interacting with the real world. Rather than relying solely on multimodal LLMs, ChatTools bridges the gap between language models and native Delphi components.
MakerAI ChatTools separates AI reasoning from execution, allowing models to invoke specialized tools only when they’re needed. The framework can process PDFs, perform OCR and image analysis, generate speech, search the web, interpret code, and even execute shell commands through a unified orchestration pipeline.
The framework includes native interfaces for PDF processing, vision, speech, web search, image and video generation, code interpretation, shell execution, and computer-use automation, making it easy to add new capabilities without changing the underlying AI model. It supports standalone automation, automatic tool orchestration, AI-driven function calling, and native multimodal processing depending on the capabilities of the connected model.
Whether you’re building document-aware assistants, vision-enabled applications, speech interfaces, or autonomous AI agents, MakerAI ChatTools provides the “eyes, ears, and hands” that transform language models into capable real-world assistants.
Explore how MakerAI ChatTools extends AI models with native Delphi capabilities.